[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6RAQJ76HT738RVE9GVYQAA0":3,"skill-same:01M6RAQJ76HT738RVE9GVYQAA0":92},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6RAQJ76HT738RVE9GVYQAA0","startup-user-simulator",null,"Simulate how five plausible customer personas experience a startup, SaaS, app, or landing page, explain why each would convert, hesitate, or leave, and produce a polished standalone HTML report. Use when Codex needs to test a live URL, localhost app, screenshot, prototype, or landing-page copy for positioning, first-impression clarity, relevance, trust, objections, conversion friction, CTA effectiveness, mobile experience, prioritized improvements, or a shareable launch-readiness report.","Nairon-AI\u002Fagentic-starter-pack","Nairon-AI","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F260662138?v=4","01M6R8PZ1Y8CSQGFN61VACZGTH","Nairon AI","01M6R8PZ6184VR3BA88YZFBC3N",4,"MIT","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fmarketing\u002Fcro\u002Fstartup-user-simulator\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"startup user simulator","startup","user","mobile","when","customer personas","standalone","URL","app","live","positioning","trust","customer","conversion","html","clarity","html report","why","how","screenshot","2026-11-10 10:12:30",false,"---\nname: startup-user-simulator\ndescription: Simulate how five plausible customer personas experience a startup, SaaS, app, or landing page, explain why each would convert, hesitate, or leave, and produce a polished standalone HTML report. Use when Codex needs to test a live URL, localhost app, screenshot, prototype, or landing-page copy for positioning, first-impression clarity, relevance, trust, objections, conversion friction, CTA effectiveness, mobile experience, prioritized improvements, or a shareable launch-readiness report.\n---\n\n# Startup User Simulator\n\nEvaluate a real product surface through five evidence-based simulated customers. Make the distinction between simulation and real user research explicit while producing concrete, prioritized fixes.\n\nRead [references\u002Fevaluation-framework.md](references\u002Fevaluation-framework.md) before scoring or writing the report.\nRead [references\u002Freport-artifact.md](references\u002Freport-artifact.md) before creating the final report file.\n\n## Workflow\n\n### 1. Establish the test\n\n- Identify the page, product, intended audience, primary conversion action, and test depth.\n- Infer missing context from the page when the inference is safe; label it clearly.\n- Ask one concise question only when the missing conversion goal or audience would materially change the evaluation.\n- Default to five personas and the primary landing-page journey.\n\nSupported inputs:\n\n- public URL or localhost app\n- screenshots or design mockups\n- pasted landing-page copy\n- repository containing a runnable frontend\n- two versions for a before\u002Fafter comparison\n\n### 2. Inspect the actual experience\n\n- Prefer an interactive browser for URLs and localhost apps.\n- Inspect desktop and mobile when both are available.\n- Review the hero, navigation, social proof, pricing, FAQ, forms, CTA destinations, error states, and important interactions relevant to conversion.\n- Record specific page evidence for every important conclusion.\n- Do not submit forms, create accounts, make purchases, send messages, or change external state unless the user explicitly requests it.\n- If only screenshots or copy are available, evaluate only what is visible and state the limitation.\n\n### 3. Build five plausible personas\n\nCreate personas after inspecting the product. Base them on the stated audience, page positioning, price, use case, and buying motion rather than generic demographics.\n\nEnsure the set contains meaningful decision differences, such as:\n\n- strongest-fit user\n- skeptical evaluator\n- budget-sensitive buyer\n- time-constrained buyer\n- adjacent or non-technical user\n\nFor each persona define the job, context, awareness level, main constraint, decision criteria, and strongest objection. Avoid stereotypes and invented biographical detail.\n\n### 4. Simulate each decision journey\n\nTrace each persona through:\n\n1. first five seconds\n2. problem and product comprehension\n3. personal relevance\n4. trust formation\n5. effort, risk, and price evaluation\n6. CTA decision\n\nSeparate observations from inferences. Tie observations to visible elements or interactions. Score with the bundled framework and label every score:\n\n> Simulated decision score — not a predicted conversion rate.\n\nNever present simulated personas as real customers, interviews, analytics, or statistically valid research.\n\n### 5. Produce the report\n\nLead with the result, not the methodology. Use this order:\n\n1. **Verdict** — one sentence on who converts and why others leave.\n2. **Biggest conversion leak** — the single highest-impact issue with evidence.\n3. **Persona scorecard** — persona, job, first impression, trust break, objection, simulated score, and decision.\n4. **Five journeys** — concise evidence-backed reasoning for each persona.\n5. **Top five fixes** — rank by expected impact and effort; include exact copy or UI changes when useful.\n6. **Fastest experiment** — one measurable test the founder can run next.\n7. **Limits** — what simulation cannot establish and what requires real users or analytics.\n\nKeep the default report compact and visually scannable. Avoid generic advice such as “improve the design” or “add social proof”; specify the element, reason, persona affected, and proposed change.\n\n### 6. Create and open the report artifact\n\n- Always create a polished standalone HTML report unless the user explicitly asks for chat-only output.\n- Write the structured analysis as JSON using the schema in `references\u002Freport-artifact.md`.\n- Run `scripts\u002Fgenerate_report.py \u003Canalysis.json> \u003Creport.html>` from this skill directory.\n- Save the final file in the workspace `outputs\u002F` directory by default, using a descriptive name such as `startup-user-simulation-example-com.html`.\n- Verify that the HTML exists and contains the verdict, five persona cards, prioritized fixes, experiment, and limitations.\n- Return a clickable absolute file link in the final response so the report opens from the Codex conversation.\n- Let the Codex app handle the local preview; do not launch an external system browser.\n- Treat the JSON as an intermediate artifact; keep it in a work or temporary directory unless the user asks for the raw data.\n\n## Modes\n\n- **quick**: Inspect the primary page and return the verdict, scorecard, and top five fixes.\n- **deep**: Inspect desktop, mobile, important interactions, pricing, and CTA destinations.\n- **mobile**: Focus on small-screen comprehension, interaction, and CTA visibility.\n- **before-after**: Compare two versions with the same personas and scoring framework.\n- **copy**: Focus on positioning, hero copy, objection handling, and CTA language.\n\nUse `quick` by default unless the user requests another mode.\n\n## Quality bar\n\n- Make every major claim traceable to page evidence.\n- Prefer five distinct decision models over five cosmetic persona variations.\n- Treat scores as structured heuristics, never behavioral forecasts.\n- Distinguish product problems from landing-page communication problems.\n- Prioritize changes a founder can actually implement.\n- End with the strongest next action, not a vague summary.\n- Deliver a report that remains readable on desktop, mobile, and when printed to PDF.\n","# Startup User Simulator\n\nEvaluate a real product surface through five evidence-based simulated customers. Make the distinction between simulation and real user research explicit while producing concrete, prioritized fixes.\n\nRead [references\u002Fevaluation-framework.md](references\u002Fevaluation-framework.md) before scoring or writing the report.\nRead [references\u002Freport-artifact.md](references\u002Freport-artifact.md) before creating the final report file.\n\n## Workflow\n\n### 1. Establish the test\n\n- Identify the page, product, intended audience, primary conversion action, and test depth.\n- Infer missing context from the page when the inference is safe; label it clearly.\n- Ask one concise question only when the missing conversion goal or audience would materially change the evaluation.\n- Default to five personas and the primary landing-page journey.\n\nSupported inputs:\n\n- public URL or localhost app\n- screenshots or design mockups\n- pasted landing-page copy\n- repository containing a runnable frontend\n- two versions for a before\u002Fafter comparison\n\n### 2. Inspect the actual experience\n\n- Prefer an interactive browser for URLs and localhost apps.\n- Inspect desktop and mobile when both are available.\n- Review the hero, navigation, social proof, pricing, FAQ, forms, CTA destinations, error states, and important interactions relevant to conversion.\n- Record specific page evidence for every important conclusion.\n- Do not submit forms, create accounts, make purchases, send messages, or change external state unless the user explicitly requests it.\n- If only screenshots or copy are available, evaluate only what is visible and state the limitation.\n\n### 3. Build five plausible personas\n\nCreate personas after inspecting the product. Base them on the stated audience, page positioning, price, use case, and buying motion rather than generic demographics.\n\nEnsure the set contains meaningful decision differences, such as:\n\n- strongest-fit user\n- skeptical evaluator\n- budget-sensitive buyer\n- time-constrained buyer\n- adjacent or non-technical user\n\nFor each persona define the job, context, awareness level, main constraint, decision criteria, and strongest objection. Avoid stereotypes and invented biographical detail.\n\n### 4. Simulate each decision journey\n\nTrace each persona through:\n\n1. first five seconds\n2. problem and product comprehension\n3. personal relevance\n4. trust formation\n5. effort, risk, and price evaluation\n6. CTA decision\n\nSeparate observations from inferences. Tie observations to visible elements or interactions. Score with the bundled framework and label every score:\n\n> Simulated decision score — not a predicted conversion rate.\n\nNever present simulated personas as real customers, interviews, analytics, or statistically valid research.\n\n### 5. Produce the report\n\nLead with the result, not the methodology. Use this order:\n\n1. **Verdict** — one sentence on who converts and why others leave.\n2. **Biggest conversion leak** — the single highest-impact issue with evidence.\n3. **Persona scorecard** — persona, job, first impression, trust break, objection, simulated score, and decision.\n4. **Five journeys** — concise evidence-backed reasoning for each persona.\n5. **Top five fixes** — rank by expected impact and effort; include exact copy or UI changes when useful.\n6. **Fastest experiment** — one measurable test the founder can run next.\n7. **Limits** — what simulation cannot establish and what requires real users or analytics.\n\nKeep the default report compact and visually scannable. Avoid generic advice such as “improve the design” or “add social proof”; specify the element, reason, persona affected, and proposed change.\n\n### 6. Create and open the report artifact\n\n- Always create a polished standalone HTML report unless the user explicitly asks for chat-only output.\n- Write the structured analysis as JSON using the schema in `references\u002Freport-artifact.md`.\n- Run `scripts\u002Fgenerate_report.py \u003Canalysis.json> \u003Creport.html>` from this skill directory.\n- Save the final file in the workspace `outputs\u002F` directory by default, using a descriptive name such as `startup-user-simulation-example-com.html`.\n- Verify that the HTML exists and contains the verdict, five persona cards, prioritized fixes, experiment, and limitations.\n- Return a clickable absolute file link in the final response so the report opens from the Codex conversation.\n- Let the Codex app handle the local preview; do not launch an external system browser.\n- Treat the JSON as an intermediate artifact; keep it in a work or temporary directory unless the user asks for the raw data.\n\n## Modes\n\n- **quick**: Inspect the primary page and return the verdict, scorecard, and top five fixes.\n- **deep**: Inspect desktop, mobile, important interactions, pricing, and CTA destinations.\n- **mobile**: Focus on small-screen comprehension, interaction, and CTA visibility.\n- **before-after**: Compare two versions with the same personas and scoring framework.\n- **copy**: Focus on positioning, hero copy, objection handling, and CTA language.\n\nUse `quick` by default unless the user requests another mode.\n\n## Quality bar\n\n- Make every major claim traceable to page evidence.\n- Prefer five distinct decision models over five cosmetic persona variations.\n- Treat scores as structured heuristics, never behavioral forecasts.\n- Distinguish product problems from landing-page communication problems.\n- Prioritize changes a founder can actually implement.\n- End with the strongest next action, not a vague summary.\n- Deliver a report that remains readable on desktop, mobile, and when printed to PDF.\n",{"name":5,"description":7},"main","c9d0c408715983e993b2f9ebffdbfa7f10153bcb","marketing\u002Fcro\u002Fstartup-user-simulator",0,"https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack","https:\u002F\u002Fgithub.com\u002FNairon-AI","https:\u002F\u002Fwww.naironai.com\u002F","Building the future of Work","2026-09-20 17:40:05",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add Nairon-AI\u002Fagentic-starter-pack --skill startup-user-simulator",{"tool":59,"command":60},"bunx","bunx skills add Nairon-AI\u002Fagentic-starter-pack --skill startup-user-simulator",{"tool":62,"command":63},"pnpm","pnpm dlx skills add Nairon-AI\u002Fagentic-starter-pack --skill startup-user-simulator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fmarketing\u002Fcro\u002Fstartup-user-simulator\u002FSKILL.md",true,[67,73,78,82,86],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"agents\u002Fopenai.yaml","REFERENCE","参考文档",265,"https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fmarketing\u002Fcro\u002Fstartup-user-simulator\u002Fagents\u002Fopenai.yaml",{"path":74,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"LICENSE","许可证",1074,"https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fmarketing\u002Fcro\u002Fstartup-user-simulator\u002FLICENSE",{"path":79,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fevaluation-framework.md",4057,"https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fmarketing\u002Fcro\u002Fstartup-user-simulator\u002Freferences\u002Fevaluation-framework.md",{"path":83,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Freport-artifact.md",3074,"https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fmarketing\u002Fcro\u002Fstartup-user-simulator\u002Freferences\u002Freport-artifact.md",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002Fgenerate_report.py","SCRIPT","脚本",18663,"https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fmarketing\u002Fcro\u002Fstartup-user-simulator\u002Fscripts\u002Fgenerate_report.py",[93,129,150,171,191,213],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":109,"publishedAt":39},"01M6RBCG630Y8X99XWR9Q4GYNY","writing-shape","Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fwriting-shape\u002FSKILL.md",[99,104],{"categoryNo":100,"categoryName":101,"taxonomyType":102,"taxonomyTypeDesc":103},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,23],"writing","writing shape","shape","notes","help","file","markdown","format","session","use","take","draft","article","material","it","about","quotes","at","candidate",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":137,"publishedAt":39},"01M6RBCCCB1KMF01P5SYGFWBSW","writing-fragments","Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions \"fragments\", \"ideate\", or \"raw material\" for writing.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fwriting-fragments\u002FSKILL.md",[135,136],{"categoryNo":100,"categoryName":101,"taxonomyType":102,"taxonomyTypeDesc":103},{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},[110,138,139,140,141,21,118,119,142,143,144,122,145,123,146,147,148,149,23],"writing fragments","grilling","ideate","develop","document","structure","ideas","as","sharp","claims","for","single",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":158,"publishedAt":39},"01M6RBC8V7NHHKMTAZB4BPXVYQ","writing-beats","Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fwriting-beats\u002FSKILL.md",[156,157],{"categoryNo":100,"categoryName":101,"taxonomyType":102,"taxonomyTypeDesc":103},{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},[110,159,160,161,119,162,163,112,164,165,166,122,167,145,168,123,169,170,148,23],"writing beats","choose","write","assemble","only","journey","next","options","end","style","narrative","argument",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":179,"publishedAt":39},"01M6RBC58SG5Y5SC4ZV4ZNEFHC","stop-slop","Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fstop-slop\u002FSKILL.md",[177,178],{"categoryNo":100,"categoryName":101,"taxonomyType":102,"taxonomyTypeDesc":103},{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},[180,181,182,110,183,184,185,186,187,119,188,189,190,148,23],"stop","stop slop","slop","content","https","text","editing","remove","prose","patterns","drafts",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":199,"publishedAt":39},"01M6RBBJTTCJ7KZCP16G9JDFZH","humanizer","Remove signs of AI-generated writing from text. Use when editing or reviewing\ntext to make it sound more natural and human-written. Based on Wikipedia's\ncomprehensive \"Signs of AI writing\" guide. Detects and fixes patterns including:\ninflated symbolism, promotional language, superficial -ing analyses, vague\nattributions, em dash overuse, rule of three, AI vocabulary words, passive\nvoice, negative parallelisms, and filler phrases.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fhumanizer\u002FSKILL.md",[197,198],{"categoryNo":100,"categoryName":101,"taxonomyType":102,"taxonomyTypeDesc":103},{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},[193,110,200,201,185,202,161,203,204,187,205,206,189,207,208,209,210,211,212,23],"code","em dash","read","edit","generated","guide","opencode","three","human","make","wikipedia","vague","dash",{"skillNo":214,"name":215,"nameZh":6,"description":216,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":217,"categories":218,"keywords":219,"publishedAt":39},"01M6RBBEQKJ5HRH8AV9J85QB1T","feedback","Prepare, deliver, and debrief timely interpersonal feedback using a question-first coaching flow, observable behavior, owned experience, and concrete impact. Use when drafting feedback, coaching managers, rehearsing a feedback conversation, praising specific behavior, or reviewing whether feedback landed.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Ffeedback\u002FSKILL.md",[],[215,220,221,222,223,224,119,225,226,227,228,229,23,230],"prepare","flow","first","question","behavior","conversation","coaching","debrief","impact","managers","deliver"]